Towards a Versatile Surface Electromyography Classification System

Barmpakos, Dimitris; Στριμπάκος, Νικόλαος; Karkanis, S.A.; Pattichis, Constantinos S.

doi:10.1007/978-3-319-32703-7_7

Cited by 5 publications

(6 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They claim that the recognition rate was as high as 99.4%, but this was only for a particular subject. Second, in [21], for eight sEMG channels, the discrete wavelet transform and SVM were used to classify the same gestures as those in this study, and the reported misclassification rate was 4.7% ± 3.7%. Third, Liu [37] employed a combination of AR model coefficients and the time domain feature set from the eight-channel sEMG signals as features, and the average recognition rate of the adaptive unsupervised classifier based on SVM was 96.6% ± 1.5%.…”

Section: Discussionmentioning

confidence: 96%

“…The two frequency-domain features were median frequency and mean power frequency [16][17][18]. The twelve time-and frequency-domain features included maximum, singular value, average energy, VAR, standard deviation, and WL of wavelet coefficients and wavelet packet coefficients [19][20][21][22][23][24][25][26]. The three nonlinear dynamic features were entropy of wavelet coefficients, entropy of wavelet packet coefficients, and maximum of Lyapunov exponent [27][28][29].…”

Section: Feature Set Computation and Reductionmentioning

confidence: 99%

“…In this study, fifteen subjects from Beijing Forestry University in China with no neurological or muscular disorders volunteered to participate in the experiments. The average age of the subjects was 23 years (range: [20][21][22][23][24][25][26][27].…”

Section: Data Collectionmentioning

confidence: 99%

See 2 more Smart Citations

Classification of surface electromyogram signals based on directed acyclic graphs and support vector machines

Hu¹,

Kan²,

Li³

2018

Turk J Elec Eng & Comp Sci

View full text Add to dashboard Cite

This paper presents a novel classification approach for surface electromyogram (sEMG) signals. The proposed classification approach involves two steps: (1) feature extraction from an sEMG, in which a 7-dimensional feature vector is extracted from 27 types of features of the sEMG by linear discriminant analysis (LDA), and (2) a novel classifier, DAGSVMerr, based on a directed acyclic graph (DAG) and support vector machine (SVM), in which a separability measure function based on erroneous recognition rates (ERRs) is defined to determine the initial operation list. The proposed approach takes advantage of the feedback idea to improve the performance of the classification. The experimental results show that the proposed approach has a better performance than traditional methods, and it achieves an average classification accuracy rate of 99.4% ± 1.3% with an error rate of 0.6%. Correct classification rates of the proposed approach are very high, and the approach can be utilized to recognize gesture instructions by analyzing sEMG signals in gesture equipment control studies.

show abstract

Section: Discussionmentioning

confidence: 96%

Section: Feature Set Computation and Reductionmentioning

confidence: 99%

See 1 more Smart Citation

Classification of surface electromyogram signals based on directed acyclic graphs and support vector machines

Hu¹,

Kan²,

Li³

2018

Turk J Elec Eng & Comp Sci

View full text Add to dashboard Cite

show abstract

“…Wavelet Packet Decomposition (WPD) is a more sophisticated analysis method that can more accurately reflect signal characteristics. The twelve time-frequency features we use include the maximum values of WT and WPD, singular values, average energy, variance, standard deviation, and WL [34][35][36][37][38][39][40][41]. In this paper, the wavelet-based sym3 is used to perform level = 3 wavelet decomposition on the EMG signal, and the third-order Symlet wavelet packet base is used to perform WPD on the EMG signal.…”

Section: Time-frequency Featuresmentioning

confidence: 99%

Exploration of Feature Extraction Methods and Dimension for sEMG Signal Classification

Wang

et al. 2019

Applied Sciences

View full text Add to dashboard Cite

It is necessary to complete the two parts of gesture recognition and wireless remote control to realize the gesture control of the automatic pruning machine. To realize gesture recognition, in this paper, we have carried out the research of gesture recognition technology based on surface electromyography signal, and discussed the influence of different numbers and different gesture combinations on the optimal size. We have calculated the 630-dimensional eigenvector from the benchmark scientific database of sEMG signals and extracted the features using principal component analysis (PCA). Discriminant analysis (DA) has been used to compare the processing effects of each feature extraction method. The experimental results have shown that the recognition rate of four gestures can reach 100.0%, the recognition rate of six gestures can reach 98.29%, and the optimal size is 516~523 dimensions. This study lays a foundation for the follow-up work of the pruning machine gesture control, and p rovides a compelling new way to promote the creative and human computer interaction process of forestry machinery.

show abstract

“…Upper limb tasks should be goal-oriented and of a standardized nature to obtain consistent performance [ 34 ]. Some previous works have evaluated the performance of similar SEMG classification systems by using the NINAPRO database [ 35 – 37 ]. However, the sEMG data contained in this database was recorded while performing non-goal-oriented actions.…”

Section: Introductionmentioning

confidence: 99%

Identification of forearm skin zones with similar muscle activation patterns during activities of daily living

Jarque-Bou

Vergara

Sancho-Bru

et al. 2018

J NeuroEngineering Rehabil

View full text Add to dashboard Cite

BackgroundA deeper knowledge of the activity of the forearm muscles during activities of daily living (ADL) could help to better understand the role of those muscles and allow clinicians to treat motor dysfunctions more effectively and thus improve patients’ ability to perform activities of daily living.MethodsIn this work, we recorded sEMG activity from 30 spots distributed over the skin of the whole forearm of six subjects during the performance of 21 representative simulated ADL from the Sollerman Hand Function Test. Functional principal component analysis and hierarchical cluster analysis (HCA) were used to identify forearm spots with similar muscle activation patterns.ResultsThe best classification of spots with similar activity in simulated ADL consisted in seven muscular-anatomically coherent groups: (1) wrist flexion and ulnar deviation; (2) wrist flexion and radial deviation; (3) digit flexion; (4) thumb extension and abduction/adduction; (5) finger extension; (6) wrist extension and ulnar deviation; and (7) wrist extension and radial deviation.ConclusionThe number of sEMG sensors could be reduced from 30 to 7 without losing any relevant information, using them as representative spots of the muscular activity of the forearm in simulated ADL. This may help to assess muscle function in rehabilitation while also simplifying the complexity of prosthesis control.

show abstract

Towards a Versatile Surface Electromyography Classification System

Cited by 5 publications

References 10 publications

Classification of surface electromyogram signals based on directed acyclic graphs and support vector machines

Classification of surface electromyogram signals based on directed acyclic graphs and support vector machines

Exploration of Feature Extraction Methods and Dimension for sEMG Signal Classification

Identification of forearm skin zones with similar muscle activation patterns during activities of daily living

Contact Info

Product

Resources

About